Bacharelado em Sistemas de Informação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/12
Siglas das Coleções:
APP - Artigo Publicado em Periódico
TAE - Trabalho Apresentado em Evento
TCC - Trabalho de Conclusão de Curso
Navegar
Item Métodos de previsão de consumo de energia elétrica residencial em grande volume de dados(2019) Carvalho, Daniel José de; Medeiros, Victor Wanderley Costa de; Gonçalves, Glauco Estácio; http://lattes.cnpq.br/6157118581200722; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/6867315638833821Electricity is one of the primary sources of energy used by humanity. Growing concern for the preservation of the environment has stimulated the search for renewable energy sources capable of reducing impacts on nature. Population growth and the increasingly frequent use of electronic devices in almost all daily activities demand the most efficient use of electricity. Due to these challenges, it is essential to carry out planning to dimen-sion the structure of generation and transmission of electric energy. One of the tools capable of assisting in this sizing is the demand forecasting. Another major challenge in this area lies in the realization of these forecasts in large data scenarios (Big Data). This work aims to evaluate the performance of two prediction methods, ARIMA andHolt-Winters, using temporal series applied to a large volume of data. The database was provided by the DEBS 2014 Grand Challenge event, which contains electricity consumption data for a large number of households for one month. For the application of the prediction methods, we used libraries in the R language. In order to process data,the Apache Spark framework was used in conjunction with the R language to parallelize the data reading processing and filtering parameters. The treated data were convertedin to time series with hourly consumption values, throughout the month comprised by theoriginal database. Predictions were made for the region of the households as a who leand each residence individually. The results showed an advantage of ARIMA versusHolt-Winters in the scenario used, using the RMSE metric as a comparative basis of performance. However, based on similar experiments found in the literature, with due proportions, both RMSE values are within an acceptable range.Item Suporte a decisão no setor sucroalcooleiro(2019) Silva, João Vitor da; Gonçalves, Glauco Estácio; http://lattes.cnpq.br/6157118581200722The sugar and alcohol sector is one of the largest agricultural sectors in Brazil. Each harvest millions of liters of ethanol and thousands of tons of sugar are imported worldwide.Despite the size of the sector, there are several problems that haunt the sugarcane producer. One is the drop in production causing sugar and ethanol production stops.This paper aims to carry out a comparative study of time series forecasting methodsin historical sugarcane production data, together with the construction of operation al indicators to aid in decision making. The database was taken from the quarterly results published by São Martinho for its investors. São Martinho is a publicly traded companyand one of the largest sugar, alcohol and energy production plants in Brazil. The R language was used to carry out the study. The experiments of this work used the predictive model SARIMA, for its almost unanimity in the forecast of agricultural yields.RMSE, ME, and MAE. In the development of the operational indicators, the waste distribution function of the SARIMA model defined along with the forecasts of the modelitself was used.At the end of all the work, the best SARIMA model was obtained for the quarterly sugarcane production data together with the indicators of fall in production: probability off all in production by 30 % and probability of fall in production below quarterly average production.